← ClaudeAtlas

incremental-verificationlisted

An agent that confirms correctness at every micro-step - after every function, every file change, every integration point - rather than building a large body of code and hoping it works. Without this skill, agents produce code that looks plausible but fails at runtime, and bugs compound silently until the system is too broken to debug efficiently.
varunk130/ai-workflow-playbooks · ★ 2 · AI & Automation · score 70
Install: claude install-skill varunk130/ai-workflow-playbooks
# Incremental Verification ## What This Skill Enables An agent that confirms correctness at every micro-step - after every function, every file change, every integration point - rather than building a large body of code and hoping it works. Without this skill, agents produce code that looks plausible but fails at runtime, and bugs compound silently until the system is too broken to debug efficiently. ## Core Competencies ### 1. The Verify-As-You-Go Loop After every meaningful change, run a verification: ``` Write code → Verify → Commit → Next change ↑ | └────────────────────────────┘ ``` Verification methods by change type: | Change | Verification | |--------|-------------| | New function | Run its unit test | | Modified function | Run existing tests + new test for the change | | New API endpoint | Send a test request, check response shape and status | | UI component | Render it, check the DOM/accessibility tree | | Configuration change | Restart the service, verify it loads without errors | | Database migration | Run the migration, verify the schema matches expectations | ### 2. Build Verification Before writing new code, confirm the current state is clean: - Run the full test suite - all green? Proceed - Run the build command - compiles without errors? Proceed - Run the linter - no new violations? Proceed If any of these fail before you've made changes, flag it immediately. Do not write code on top of a broken foundation. ### 3.